DY-LUT：用于实时水下图像增强的深度感知YCbCr查找表

中文摘要 AI 辅助

水下图像增强面临空间不均匀、波长依赖衰减的挑战。传播距离和波长决定这种退化，而YCbCr将亮度与色度分离以进行恢复。我们提出了DY-LUT，一种用于实时增强的深度感知YCbCr查找表框架。双分支编码器从图像和深度特征预测图像级融合权重和像素级退化指数对。这些量调节可学习的4D查找表，随后进行轻量级局部细化。DY-LUT保留了传统查找表的效率，同时实现了深度条件下的空间自适应恢复。在外部提供深度的情况下，其具有356万个参数的增强网络在UIEB-90和LSUI上实现了有竞争力的质量，并且比代表性的高容量基线快9至304倍。自适应推理进一步保持了4K UIQAD图像的实时性能（约7毫秒）。DY-LUT也有利于下游检测和特征匹配。消融实验表明，对于深度条件查找，YCbCr比RGB是更有效的基础，而联合学习的指数进一步改善了自适应查询。这些结果为在实际平台上进行高效的水下图像增强提供了一条基于物理的途径。

英文摘要

Underwater image enhancement is challenged by spatially non-uniform, wavelength-dependent attenuation. Propagation distance and wavelength govern this degradation, while YCbCr separates luminance from chrominance for restoration. We propose DY-LUT, a depth-aware YCbCr lookup-table framework for real-time enhancement. A dual-branch encoder predicts image-level fusion weights and a joint pair of pixel-wise degradation indices from image and depth features. These quantities condition learnable 4D LUTs, followed by lightweight local refinement. DY-LUT preserves traditional LUT efficiency while enabling depth-conditioned, spatially adaptive restoration. With externally supplied depth, its 3.56M-parameter enhancement network achieves competitive quality on UIEB-90 and LSUI and runs $9$--$304\times$ faster than representative high-capacity baselines. Adaptive inference further maintains real-time performance ($\sim7$ ms) for 4K UIQAD images. DY-LUT also benefits downstream detection and feature matching. Ablations show that YCbCr is a more effective basis than RGB for depth-conditioned lookup, while the jointly learned indices further improve adaptive querying. These results provide a physically grounded route to efficient UIE on practical platforms.

发表机构

• Shandong University（山东大学）
• The Hong Kong Polytechnic University（香港理工大学）
• Mohamed bin Zayed University of Artificial Intelligence（穆罕默德·本·扎耶德人工智能大学）

机构由 AI 辅助整理，请以论文原文为准。